Microstructure order flow: statistical and economic evaluation of nonlinear forecasts

In this paper we propose a novel extension of the standard market microstructure order flow model by incorporating non-linearities into the order flow-exchange rate relationship. This important issue has not been accounted for in the existing empirical literature. We investigate this issue using a new data set and focusing on out-of-sample forecasts. Forecasting power is measured using standard statistical tests and, additionally, using an alternative approach based on measuring the economic value of forecasts after building a portfolio of assets. While there is little statistical value in conditioning on our proposed models, its economic value is significantly high.